TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videos

Annotate better with CVAT, the industry-leading data engine for machine learning. Used and trusted by teams at any scale, for data of any scale.

Tensors and Dynamic neural networks in Python with strong GPU acceleration

DirectML is a high-performance, hardware-accelerated DirectX 12 library for machine learning. DirectML provides GPU acceleration for common machine learning tasks across a broad range of supported …

ByteTrack: Multi-Object Tracking by Associating Every Detection Box

Bot Dofus 2 en Python 3

📚 Jupyter notebook tutorials for OpenVINO™

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

A deep learning library for video understanding research.

Serve, optimize and scale PyTorch models in production

Common utilities for ONNX converters

CUDA integration for Python, plus shiny features

[NeurIPS'21] Projected GANs Converge Faster

TensorRT is a C++ library for high performance inference on NVIDIA GPUs and deep learning accelerators.

An easy to use PyTorch to TensorRT converter

Torch video loading library with support for GPU decoding

Real-time multi-person tracker using YOLO v5 and deep sort

YOLOv5 in PyTorch > ONNX > CoreML > TFLite

ready-to-use RTSP server and RTSP proxy that allows to read and publish video and audio streams via UDP and TCP

⚡ Useful scripts when using TensorRT

DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution

An implementation of SoftDTW for PyTorch.

Script for uploading large files to AWS Glacier

PyTorch Implementation of "Resource Efficient 3D Convolutional Neural Networks", codes and pretrained models.

A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch